Re: [R] Generic code for simulating from a distribution.
Hi, have a look at the packages distr and distrSim which are on CRAN. hth Matthias - original Nachricht Betreff: [R] Generic code for simulating from a distribution. Gesendet: Mo, 10. Apr 2006 Von: [EMAIL PROTECTED] Hello all, I have the code below to simulate samples of certain size from a particular distribution (here,beta distribution) and compute some statistics for the samples. betasim2-function(nsim,n,alpha,beta) { sim-matrix(rbeta(nsim*n,alpha,beta),ncol=n) xmean-apply(sim,1,mean) xvar-apply(sim,1,var) xmedian-apply(sim,1,median) simset-data.frame(sampleno=seq1:nsim),means=xmean,vars=xvar,medians=xmedian ) return(simset) } I can write a similar coding for any distribution individually. Now, I would like to have a generic code, say if I specify the distribution with the parameters and simulation and sample size I would like to have the simulations done for the mentioned distribution and the statistics performed. I would appreciate any help in doing so? Thanks for your time. Mathangi Mathangi Gopalakrishnan Graduate student Dept of Mathematics and Statistics University of Maryland, Baltimore County Baltimore, MD __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html --- original Nachricht Ende __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Primitives
You need ls(all=TRUE) as some (12) are 'dot-names'. I just used foo - ls(package:base, all =TRUE) pr - foo[sapply(foo, function(x) is.primitive(get(x, package:base)))] and got 152. There is a description in the `Writing R Extensions' manual, but it is incomplete, and another classified list in tests/primitive-funs.R (also incomplete). On Sun, 9 Apr 2006, Duncan Murdoch wrote: On 4/9/2006 5:57 PM, Diethelm Wuertz wrote: Duncan Murdoch wrote: On 4/9/2006 5:46 AM, Diethelm Wuertz wrote: How one can make a list of all functions in R's base package which are given as Primitives like abs, sqrt cumsum (but not log) ? There's an is.primitive() test function; you just need to Sorry when I ask again, how to list all functions in R's base installation? ls(baseenv()) or ls(package:base) will give you all their names. So you need to use something like names - ls(baseenv()) result - rep(FALSE, length(names)) for (i in seq(along=names)) { result[i] - is.primitive(get(names[i], envir=baseenv())) } names[result] Duncan Murdoch -- Brian D. Ripley, [EMAIL PROTECTED] Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UKFax: +44 1865 272595 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] using 'sum' function in writing a function
Hi, I am writing a function that includes 'sum' function such as: f-function(x){ c-c(-1,0,1) f-sum(c+x) } expecting f to be -1+x+0+x+1+x=3x. But I found out that f is sum(x). So, f is always a scalar, which means that f(c(0,1)) is not a vector as c(0,3), but 3(0+1)=3. I would like to ask you helping me in solving this problem. I would like to thank you in advance. Sungsu. UC riverside. __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] passing known medoids to clara() in the cluster package
DylanB == Dylan Beaudette [EMAIL PROTECTED] on Sun, 9 Apr 2006 19:28:44 -0700 writes: DylanB Greetings, I have had good success using the clara() DylanB function to perform a simple cluster analysis on a DylanB large dataset (1 million+ records with 9 variables). DylanB Since the clara function is a wrapper to pam(), DylanB which will accept known medoid data - I am wondering DylanB if this too is possible with clara() ... The DylanB documentation does not suggest that this is DylanB possible. indeed, it doesn't -- because it's not yet possible. I (as maintainer of cluster) had added the ``known medoid'' option to pam() a while ago last June (for cluster version 1.10.0), and had left a note my TODO file to do the same for clara(). Unfortunately it's not true that clara() was a wrapper to pam() as you state above. Given your wish and clear use case situation, I'm more motivated to approach this particular 'TODO' item! Martin Maechler, ETH Zurich DylanB Essentially I am trying to implement a supervised DylanB classification of numerous geographic data DylanB layers. The unsupervised approach using clara() DylanB works well, but I feel the output classes would be DylanB more meaningful if I were able to let clara() know DylanB about the classes that I have in mind. DylanB Is this at all feasible, or am I trying to DylanB accomplish something that is not possible? __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] The mysterious e1071
On Saturday 08 April 2006 11:51, Chelsea Ellis wrote: Hi, I'm trying to use the svm function in R, but I can't find the e1071 package. When I type library(e1071), I get the error message that the package doesn't exist. I've searched all over the CRAN website, but I can't find anything. Did it change names? Thanks for your help, Chelsea You'll have to download it off CRAN. It IS there. Go to CRAN, choose your server, and then on the left pane, you will see a link named packages. The link will be http://[your server name]/src/contrib/PACKAGES.html. Chose that. On the right pane, which is not visually well differentiated from the rest of the page, scroll down. e1071 is there right at the beginning of the packages whose names begin with e. Have fun, JD __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] some output is missing -- not getting the full anova table
I have just started using R and am stumped over something: I am using the lme4 package, using lmer (and putting it in to fit0.lmer ) and then I do an anova, but I am not getting the full table. This is what I get: fit0.lmer - lmer(subj.prob.rev ~ semantic.class + bipron.rec + item.order + (1|subject) + (1|verb), data=data) anova(fit0.lmer) Analysis of Variance Table Df Sum Sq Mean Sq semantic.class 3 5401.7 1800.6 bipron.rec 1 22739.3 22739.3 item.order 1 7225.2 7225.2 Can anyone help? Marilyn __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] installing problem
Dear R users a problem I encountered while installing fMultivar, I would appriciate any help with this. install.packages (fMultivar, dependencies=TRUE) Warning in install.packages(fMultivar, dependencies = TRUE) : argument 'lib' is missing: using /usr/local/lib/R/site-library also installing the dependencies 'fBasics', 'fCalendar', 'fSeries' trying URL 'http://cran.cnr.Berkeley.edu/src/contrib/fBasics_221.10065.tar.gz' Content type 'application/x-tar' length 3111632 bytes opened URL == downloaded 3038Kb trying URL 'http://cran.cnr.Berkeley.edu/src/contrib/fCalendar_221.10065.tar.gz' Content type 'application/x-tar' length 485586 bytes opened URL == downloaded 474Kb trying URL 'http://cran.cnr.Berkeley.edu/src/contrib/fSeries_221.10065.tar.gz' Content type 'application/x-tar' length 1594150 bytes opened URL == downloaded 1556Kb trying URL 'http://cran.cnr.Berkeley.edu/src/contrib/fMultivar_221.10065.tar.gz' Content type 'application/x-tar' length 1152747 bytes opened URL == downloaded 1125Kb * Installing *source* package 'fBasics' ... ** libs /usr/lib/R/bin/SHLIB: line 102: make: command not found ERROR: compilation failed for package 'fBasics' ** Removing '/usr/local/lib/R/site-library/fBasics' * Installing *source* package 'fCalendar' ... ** libs /usr/lib/R/bin/SHLIB: line 102: make: command not found ERROR: compilation failed for package 'fCalendar' ** Removing '/usr/local/lib/R/site-library/fCalendar' * Installing *source* package 'fSeries' ... ** libs /usr/lib/R/bin/SHLIB: line 102: make: command not found ERROR: compilation failed for package 'fSeries' ** Removing '/usr/local/lib/R/site-library/fSeries' * Installing *source* package 'fMultivar' ... ** libs /usr/lib/R/bin/SHLIB: line 102: make: command not found ERROR: compilation failed for package 'fMultivar' ** Removing '/usr/local/lib/R/site-library/fMultivar' The downloaded packages are in /tmp/Rtmpr75wQe/downloaded_packages Warning messages: 1: installation of package 'fBasics' had non-zero exit status in: install.packages(fMultivar, dependencies = TRUE) 2: installation of package 'fCalendar' had non-zero exit status in: install.packages(fMultivar, dependencies = TRUE) 3: installation of package 'fSeries' had non-zero exit status in: install.packages(fMultivar, dependencies = TRUE) 4: installation of package 'fMultivar' had non-zero exit status in: install.packages(fMultivar, dependencies = TRUE) thank you - [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] some output is missing -- not getting the full anova table
marilyn ford m.ford at griffith.edu.au writes: I have just started using R and am stumped over something: I am using the lme4 package, using lmer (and putting it in to fit0.lmer ) and then I do an anova, but I am not getting the full table. This is what I get: fit0.lmer - lmer(subj.prob.rev ~ semantic.class + bipron.rec + item.order + (1|subject) + (1|verb), data=data) anova(fit0.lmer) Analysis of Variance Table Df Sum Sq Mean Sq semantic.class 3 5401.7 1800.6 bipron.rec 1 22739.3 22739.3 item.order 1 7225.2 7225.2 DF and p-values are currently not shown because of ongoing restauration work. Douglas Bates Deepayan believe in better nothing than possibly slightly off. See for example http://finzi.psych.upenn.edu/R/Rhelp02a/archive/49633.html Shop will be re-opened as soon as smoke has settled. Dieter __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] SE estimates for treatment groups from nlme
Katherine A Grieve grieve at u.washington.edu writes: I am wondering how to obtain SE estimates for fixed effects from a nonlinear mixed effects model? It's a bit of fiddling, but there is an example coming close to what you want on page 373 of Pinheiro/Bates, and in file \library\nlme\scripts\ch08.R, section 8.2. And don't forget that you can use intervals on nlme-results. Dieter __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Calculation of r.squared for linear model with offset
On Sun, 9 Apr 2006, Ross Darnell wrote: R^2 for a model is usually defined as 1-RSS/TSS where TSS is the SS about the mean and RSS is the residual SS from the model. Not when there is no intercept or where there is an offset in the model. Consider the model in R z - runif(20) y - z+rnorm(20) my.model - lm(y~offset(z)) summary(my.model)$r.squared Here the RSS is equivalent to the TSS and gives 0 when it should (IMHO and a few others perhaps) be 1 - RSS/TSS(corrected for the mean only) RSS = sum(resid(my.model)^2) TSS = sum((y-mean(y))^2) Those are not the correct formulae in the presence of an offset. Have I missed this somewhere in the FAQ's or elsewhere? Elsewhere. The offset is subtracted from y. -- Brian D. Ripley, [EMAIL PROTECTED] Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UKFax: +44 1865 272595 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] using 'sum' function in writing a function
skim033 at student.ucr.edu writes: Hi, I am writing a function that includes 'sum' function such as: f-function(x){ c-c(-1,0,1) f-sum(c+x) } expecting f to be -1+x+0+x+1+x=3x. But I found out that f is sum(x). So, f is always a scalar, which means that f(c(0,1)) is not a vector as c(0,3), but 3(0+1)=3. I would like to ask you helping me in solving this problem. I would like to thank you in advance. Looks like you are infected from other programming languages where in a function foo you must do a foo = ... to assign the return value. In R, this is a no-no, giving some mind-twisting recursion. And don't use c as a variable name. And parameters in sum() are comma separated, sum(c+x) is redundant. f-function(x){ c1 - c(-1,0,1) sum(c1,c1) } f(12) Dieter __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Legend in the outer margin
Dear Rs I have a 3x3 multiple plot. I would like to have a overall legend in the outer right margin. From the help archive, I found that it can be done by setting par(xpd=NA). However, I couldn't find the correct values for x and y co-ordinates for the legend. Please find the code snippet below: par(mfrow=c(3,3), mar=c(4,4,0.9,0.5), oma=c(1,2,2,4),cex.main=1.1) *postscript(*file=epsfile,onefile=FALSE,horizontal=TRUE*)* /* some plotting */ par(xpd=NA) legend(legend=c(2h-opt Exact,1-shift Exact,2p-opt Exact), lty=c(solid,dashed,dotdash),lwd=c(2,2,2),col=c(red,green,black), bty=n,cex=0.8) Thanks in advance Prasanna [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Handling of NA ´s in the matrix multiplicati on function
Hi! Is there a way of handling NA´s in the matrix multiplication function '%*%'? I cant find anything concerning this in the help files. I´m thinking of some sort of setting such as na.rm=T. Thanks before hand to anyone how can help me! Fredrik Thuring, Junior Business Researcher __ Codan Forsikring, Gammel Kongevej 60, DK-1790 Copenhagen V tel: +45 33 55 26 63, fax: +45 33 55 21 22 e-mail: [EMAIL PROTECTED] http://www.codan.dk -- This e-mail and any attachment may be confidential and may a...{{dropped}} __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Weights in glmmPQL
Hello, I am using the R function glmmPQL to fit a logistic GLMM, with weights. I am finding that I get fairly different parameter estimates in glmmPQL from fitting the full dataset (with no weight statement) and an equivalent, shorter dataset with the weights statement. I am using the weights statement in the 'glmmPQL' function exactly as in the 'glm' function. I also tested my dataset in the glm function and successfully got the correct results using the full (with no weights) and the shorter dataset (with weights). Is the weight statement in glmmPQL intended to be applied in a different way to a dataset than how it is used in the glm function? Thank-you for your help and any suggestions, Kerrie + This mail has been sent through the MPI for Demographic Rese...{{dropped}} __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] how to figure out skewness
I think it is simply, but I cannot find the method to figure out skewness. Thanks! [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] how to figure out skewness
RSiteSearch(skewness) On 4/10/06, Jian Zhang [EMAIL PROTECTED] wrote: I think it is simply, but I cannot find the method to figure out skewness. Thanks! [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] how to figure out skewness
you can transform the variable x down the ladder if it is positive skew (x^0.5,x^ -1...)and up the ladder if x is negative skew ( etc, x^2 ,x^3...). The book An R and S-PLUS Companion To Applied Regression has a section to deal with the data transformation.Especiall P109 is about transformation for normality and symmetry. Hope this helps. 2006/4/10, Jian Zhang [EMAIL PROTECTED]: I think it is simply, but I cannot find the method to figure out skewness. Thanks! [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- 黄荣贵 Deparment of Sociology Fudan University __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Upadating windows shortcuts after upgrade
Dear R users, I was just wondering, if anybody has a simple solution to the following problem: I have just installed R 2.2.1 next to R 2.1.1 (in different folder, of course) (but the versions do not really matter) on WinXP. I have different R projects in different folders and in each folder, I have (among all other things) .Rdata file, .Rhistory file and a an R 2.1.1 shortcut, which has the folder in which it is as a start (working) folder. What I would like to to now (after installing a new version) is to copy each shortcut, rename the copy to R 2.2.1 and change the target program from R 2.1.1 to R 2.2.1. I would like to do this automtically for all R 2.1.1 shortcuts on my computer. Thanks in advance for any ideas! Best regards, Ales Ziberna __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Legend in the outer margin
Prasanna wrote: Dear Rs I have a 3x3 multiple plot. I would like to have a overall legend in the outer right margin. From the help archive, I found that it can be done by setting par(xpd=NA). However, I couldn't find the correct values for x and y co-ordinates for the legend. Please find the code snippet below: par(mfrow=c(3,3), mar=c(4,4,0.9,0.5), oma=c(1,2,2,4),cex.main=1.1) *postscript(*file=epsfile,onefile=FALSE,horizontal=TRUE*)* /* some plotting */ par(xpd=NA) You get the user coordinates of the plotting region by par(usr) Now simply make the legend right of that plotting region, e.g. with x corrdinates at par(usr)[2] + epsilon and y coordinates at mean(par(usr)[3:4]) Uwe Ligges legend(legend=c(2h-opt Exact,1-shift Exact,2p-opt Exact), lty=c(solid,dashed,dotdash),lwd=c(2,2,2),col=c(red,green,black), bty=n,cex=0.8) Thanks in advance Prasanna [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Upadating windows shortcuts after upgrade
If you are using XP then create a shortcut to Rgui.bat, which can be found in: http://cran.r-project.org/contrib/extra/batchfiles/ 0.2-7 is the most recent. When you install R it saves in the registry the R version and Rgui.bat looks that up and runs that version thereby giving you the last version you installed. Rcmd.bat, also in batchfiles, does the same for running R from the command line. You can use Rversion.bat (or the gui version of that: Rversion.hta), both from batchfiles as well, to change which version you want it to use in the case that you have multiple versions of R on your system. There are also a number of other tools in the batchfiles collection that can be of use in administering R on XP. The README in batchfiles has more info. On 4/10/06, Ales Ziberna [EMAIL PROTECTED] wrote: Dear R users, I was just wondering, if anybody has a simple solution to the following problem: I have just installed R 2.2.1 next to R 2.1.1 (in different folder, of course) (but the versions do not really matter) on WinXP. I have different R projects in different folders and in each folder, I have (among all other things) .Rdata file, .Rhistory file and a an R 2.1.1 shortcut, which has the folder in which it is as a start (working) folder. What I would like to to now (after installing a new version) is to copy each shortcut, rename the copy to R 2.2.1 and change the target program from R 2.1.1 to R 2.2.1. I would like to do this automtically for all R 2.1.1 shortcuts on my computer. Thanks in advance for any ideas! Best regards, Ales Ziberna __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Legend in the outer margin
Uwe Ligges ligges at statistik.uni-dortmund.de writes: You get the user coordinates of the plotting region by par(usr) Now simply make the legend right of that plotting region, e.g. with x corrdinates at par(usr)[2] + epsilon and y coordinates at mean(par(usr)[3:4]) I always found it ugly that this depends on the last plotted figure in an array, but I wanted to position my legend independent of it at an absolute position in device space. What's the best way to achieve this? par(mfrow=c(3,3), mar=c(4,4,0.9,0.5), oma=c(5,2,5,10),cex.main=1.1) n=7 # Legend should be positioned independent of n for (i in 1:n){ plot(rnorm(20),ylim=c(-3,3)) } # ... just the idea reset_to_01_coordinates() par(xpd=NA) leg = legend(0.9,0.5, # Should be seen as absolute in 0/1 coords c(2h-opt Exact,1-shift Exact,2p-opt Exact), lty=c(solid,dashed,dotdash),lwd=c(2,2,2), col=c(red,green,black), bty=n,cex=0.8) Dieter __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] fdim questions
R-users: My problem: the package fdim (which measures fractal dimensions of datasets) apparently prefers 3-D (XYZ) datasets. I'm trying to measure the information dimension (a type of fractal dimension) of a 2-D (XY) dataset. Here's some examples of the preferred 3-D data (XYZ): library(fdim) XYZ - (makehplane(NumN=300, DimM=3, Longit=300)) fdim(XYZ,q=0.99,PlotF=TRUE) Here's an example of the type of data I have: library(fdim) X- sample(1:1000,size=300,replace=TRUE) Y- sample(1:500,size=300,replace=TRUE) XY- matrix(c(X,Y),nrow=300) fdim(XY,q=0.99,PlotF=TRUE) My question is this: since fdim prefers XYZ data, is it invalid to use fdim to measure the fractal dimension of XY data? What I have is XY position data of individual trees in a section of forest. I'd like to measure the information dimension of the distribution of trees. The reason I'm asking my question is that fdim returns consistently higher dimension numbers than do other fractal-measuring programs. However, those other programs measure the fractal dimension of bitmaps, not datasets, and have a problem with resolution--many of the points on the bitmap overlap, making it impossible to measure the dimension of those points. Therefore, I'd like to measure the information dimension using a program that uses datasets, not bitmaps. Thanks for your input. Jim Milks Graduate Student Environmental Sciences Ph.D. Program Wright State University Dayton, OH 45435 [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] multicomp
Is there a multicomp() function in R as in S plus? Thanks ../Murli __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] TukeyHSDs function (pgirmess package)
Dear R-help, I have been trying to use the TukeyHSDs function in the pgirmess package to quickly extract all significant pairwise comparisons in an aov object. However, it seems that this function isn't working as intended when only the two last populations means being tested are significant. An example of this can be seen below: numbers-c(464,482,453,434,495,487) group-gl(3,2,label=c(A,B,C)) testobject-aov(numbers~group) result-TukeyHSD(testobject,conf.level=0.95) error-TukeyHSDs(result) error$group[,1] Error in error$group[, 1] : incorrect number of dimensions To illustrate the normal function, the data set below can be used. numbers-c(845,829,682, 689,581,495) Is there something wrong with this function? Or is there a better way to extract significant comparisons from a tukey test? Cheers, Rune --- Rune Vejen Petersen, M.Sc.Eng. Statens Serum Institute Dept. of Infectious Disease Immunology Artillerivej 5, 81/344 DK-2300 Copenhagen [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] regression/step coefficients extraction
Hi list, I'm looking for a way to easily extract regression p-values and export them to one file for further evaluation. Here is the problem. I use lm() and step() to get my regression parameters/coefficients. after that I can extract them with summary(lm-results)$coefficients[,4] so far so good but it seems that if a value is not significant it is dropped from the table/matrix so the previous command yields no consistent results with respect to the order of appearance. so I can get p-values for one regression being: a b c d .01 .01 .01 .01 and the next a b d .01 .01 .01 so it's not easy to match them up correctly, because these shifts in order or the lack of NA or empty spaces. I would like an output to text file in this form independent parameters: a b c p-values: .01 .02 .01 .01 NA .01 ... etc Any ideas to get a nice (and easy) output file where the dropped values are filled in with NA and keeping the order and labels ok... ? Best regards, Koen __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Fourier / Bandpass filter help?
List, I am trying to apply some digital signal analysis methods to IPv4 networks. Specifically, I have had some success using the Fast Fourier Transform in R to find periodic events in IPv4 network traffic by producing periodograms. I store network traffic in a mysql database so I have been using RMySQL to generate a data frame of [timestamp,events] (the FFT is run on the vector of events). Generating a periodogram in this case tells you that you have some periodic event occurring on your network (such as a keepalive signal from an instant messaging program) but it doesn't tell you anything more. It would be useful to figure out which events in the network log being analyzed are responsible for the peak in the periodogram--e.g. which IPs are involved in some periodic activity. So, I think what I want to do is take a subset of the vector produced by the FFT and go from that back to the initial data frame of [timestamp,events], from which I can go back to the source data and pull out the IPs and so forth. How can I do this? My roommate (an aero engineer) has recommended that I look into implementing a bandpass filter but I'm finding the material to be way over my head. I'm at the limits of my expertise (I am not an engineer :) so if anyone just wants to point me at the topics I need to study, that would be fine--although pointing out some specific examples would be great as well. Thanks, Pete - [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Re : AUC under spline curve
## simulated data... x - runif(100) y - rnorm(100) ## spline fit... m - gam(y~s(x,k=6,fx=TRUE)) ## trapezoidal integration ... n - 1000 ## number of points in trap. approx pd - data.frame(x=seq(0,1,length=n)) dx - pd$x[2]-pd$x[1] f - predict.gam(m,pd) w - rep(dx,n);w[1]-w[n] - w[2]/2 ## trapezoidal weights sum(w*f) ## integral ## ... same again with standard error... Xf - predict.gam(m,pd,type=lpmatrix) t(w)%*%Xf%*%coef(m) ## integral sqrt(t(w)%*%Xf%*%m$Vp%*%t(Xf)%*%w) ## its standard error best, Simon - Simon Wood, Mathematical Sciences, University of Bath, Bath BA2 7AY - +44 (0)1225 386603 www.maths.bath.ac.uk/~sw283/ On Mon, 10 Apr 2006 [EMAIL PROTECTED] wrote: Dear R list, I have fitted cubic regression spline with fixed degree of freedom to a set of data using package mgcv. Now I want to calculate the area under the spline curve. Someone has suggested me to use trapezoidal rule. Do you know if someone has written a package that will carry out that analysis, and where can I download it ? Thanks in advance. Stella __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] dot diagram
A basic implementation of this is the dots function in the TeachingDemos package. -- Gregory (Greg) L. Snow Ph.D. Statistical Data Center Intermountain Healthcare [EMAIL PROTECTED] (801) 408-8111 -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Jinsong Zhao Sent: Sunday, April 09, 2006 12:07 AM To: R-help Subject: [R] dot diagram Hi, I am wondering whether there is a function that could plot a dot diagram like the output of following code. Thanks in advance! Best wishes! Jinsong -my dirty code here- mydata - c(26,26,27,27,27,27,28,28,28,28,28,28,28,28,28, 28,28,28,28,29,29,29,29,29,29,29,29,29,29,29, 30,30,30,30,30,30,30,30,31,31,31,31,32,33,33, 33,34,34,35,43) my.dot.plot - function(x, ...) { x.table - table(x) x.x - as.numeric(names(x.table)) x.y - as.numeric(x.table) n - length(x.x) x.final - NULL for (i in 1:n) { tmp - data.frame(x=rep(x.x[i], x.y[i]), y=1:x.y[i]) x.final - rbind(x.final, tmp) } plot(x.final, yaxt=n, ylab=, pch=19, frame.plot=FALSE, ...) } my.dot.plot(mydata, xlab =speed, xlim=c(25,45)) __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] SE estimates for treatment groups from nlme
I have looked at that example on p. 373, however it still does not help me to get the stand errors i need. In my case, with the 18 different groups, I am combining more than just the (intercept) term with one other row in the Summary tTable. It is no problem to form linear combinations of the coefficients, but the SE in the tTable cannot just be combined. Similarly, intervals just gives me CI for each entry (row) in the tTable but these are not the group estimates that I am looking for. An example to illustrate what i mean the rows of the tTable would be labeled something like this (A=2 levels, B=3 levels, C=3 levels): Fixed Effects: (Asym~A*B*C) Value SE Asym.(intercept)x1 Asym.A1 x2 Asym.B1 x3 Asym.B2 x4 Asym.C1 x5 Asym.C2 x6 Asym.A1B1 x7 Asym.A1B2 x8 Asym.A1C1 x9 Asym.A1C2 x10 Asym.B1C1 x11 Asym.B2C1 x12 Asym.B1C2 x13 Asym.B2C2 x14 etc... So, to get an estimate for the groups I form linear combinations e.g.: Group A2,B1,C1 = x1 + x3 + x5 + x11 I am combining 4 coefficients to get the group mean -- is there a way to get the corresponding SE. It is definitely not a linear combination of the SE listed in the tTable. And, intervals just gives me a CI for each entry (row) in the table, not the linear combinations which form my groups. Thanks again. Katie - It's a bit of fiddling, but there is an example coming close to what you want on page 373 of Pinheiro/Bates, and in file \library\nlme\scripts\ch08.R, section 8.2. And don't forget that you can use intervals on nlme-results. __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] error message explanation for lmer
I am getting the following error message using the lmer function for mixed models with method=Laplace: nlminb returned message false convergence (8) in: LMEopt(x=mer,value=cv) Could anyone explain what this means, and how I might overcome (or track down) the problem? Bill Shipley [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Legend in the outer margin
The cnvrt.coords function in the TeachingDemos package may be of help. Here is an example of possible use (just change the .9 and .7 to where ever on the page you want the legend): par(mfrow=c(3,3), mar=c(4,4,0.9,0.5), oma=c(1,2,2,4),cex.main=1.1) for (i in 1:9){ x - runif(25,1,10) y - 3+ i*x + rnorm(25) plot(x,y) } par(xpd=NA) tmp - cnvrt.coords(.9,.7, 'tdev')$usr legend(tmp,legend=c(2h-opt Exact,1-shift Exact,2p-opt Exact), lty=c(solid,dashed,dotdash),lwd=c(2,2,2),col=c(red,green,blac k), bty=n,cex=0.8) -- Gregory (Greg) L. Snow Ph.D. Statistical Data Center Intermountain Healthcare [EMAIL PROTECTED] (801) 408-8111 -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Dieter Menne Sent: Monday, April 10, 2006 7:40 AM To: r-help@stat.math.ethz.ch Subject: Re: [R] Legend in the outer margin Uwe Ligges ligges at statistik.uni-dortmund.de writes: You get the user coordinates of the plotting region by par(usr) Now simply make the legend right of that plotting region, e.g. with x corrdinates at par(usr)[2] + epsilon and y coordinates at mean(par(usr)[3:4]) I always found it ugly that this depends on the last plotted figure in an array, but I wanted to position my legend independent of it at an absolute position in device space. What's the best way to achieve this? par(mfrow=c(3,3), mar=c(4,4,0.9,0.5), oma=c(5,2,5,10),cex.main=1.1) n=7 # Legend should be positioned independent of n for (i in 1:n){ plot(rnorm(20),ylim=c(-3,3)) } # ... just the idea reset_to_01_coordinates() par(xpd=NA) leg = legend(0.9,0.5, # Should be seen as absolute in 0/1 coords c(2h-opt Exact,1-shift Exact,2p-opt Exact), lty=c(solid,dashed,dotdash),lwd=c(2,2,2), col=c(red,green,black), bty=n,cex=0.8) Dieter __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] SE estimates for treatment groups from nlme
Hi Katie, maybe the easiest solution is to create a new factor that corresponds to the combinations of the three factors A, B and C. A quick and dirty way to create such a factor is: ABC - factor(paste(A, x, B, x, C, sep = )) ABC and then fit the model using the variable ABC instead of A*B*C. Christian __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] seq
Can someone, please, help explain to me why the following two calls return the same set: seq(from=as.POSIXlt('2005-12-4'), to=as.POSIXlt('2006-4-2'), by='weeks') [1] 2005-12-04 EST 2005-12-11 EST 2005-12-18 EST 2005-12-25 EST [5] 2006-01-01 EST 2006-01-08 EST 2006-01-15 EST 2006-01-22 EST [9] 2006-01-29 EST 2006-02-05 EST 2006-02-12 EST 2006-02-19 EST [13] 2006-02-26 EST 2006-03-05 EST 2006-03-12 EST 2006-03-19 EST [17] 2006-03-26 EST 2006-04-02 EST seq(from=as.POSIXlt('2005-12-4'), to=as.POSIXlt('2006-4-9'), by='weeks') [1] 2005-12-04 EST 2005-12-11 EST 2005-12-18 EST 2005-12-25 EST [5] 2006-01-01 EST 2006-01-08 EST 2006-01-15 EST 2006-01-22 EST [9] 2006-01-29 EST 2006-02-05 EST 2006-02-12 EST 2006-02-19 EST [13] 2006-02-26 EST 2006-03-05 EST 2006-03-12 EST 2006-03-19 EST [17] 2006-03-26 EST 2006-04-02 EST seq function (...) UseMethod(seq) environment: namespace:base I am using R 2.2.1 on linux. Why isn't 2006-04-09 in the response of the second call? __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] seq
Its undoubtedly a timezone or daylight savings time issue. Use this instead: seq(from=as.Date('2005-12-4'), to=as.Date('2006-4-9'), by='weeks') [1] 2005-12-04 2005-12-11 2005-12-18 2005-12-25 2006-01-01 [6] 2006-01-08 2006-01-15 2006-01-22 2006-01-29 2006-02-05 [11] 2006-02-12 2006-02-19 2006-02-26 2006-03-05 2006-03-12 [16] 2006-03-19 2006-03-26 2006-04-02 2006-04-09 and read the R News 4/1 help desk article to learn more about this. On 4/10/06, Omar Lakkis [EMAIL PROTECTED] wrote: Can someone, please, help explain to me why the following two calls return the same set: seq(from=as.POSIXlt('2005-12-4'), to=as.POSIXlt('2006-4-2'), by='weeks') [1] 2005-12-04 EST 2005-12-11 EST 2005-12-18 EST 2005-12-25 EST [5] 2006-01-01 EST 2006-01-08 EST 2006-01-15 EST 2006-01-22 EST [9] 2006-01-29 EST 2006-02-05 EST 2006-02-12 EST 2006-02-19 EST [13] 2006-02-26 EST 2006-03-05 EST 2006-03-12 EST 2006-03-19 EST [17] 2006-03-26 EST 2006-04-02 EST seq(from=as.POSIXlt('2005-12-4'), to=as.POSIXlt('2006-4-9'), by='weeks') [1] 2005-12-04 EST 2005-12-11 EST 2005-12-18 EST 2005-12-25 EST [5] 2006-01-01 EST 2006-01-08 EST 2006-01-15 EST 2006-01-22 EST [9] 2006-01-29 EST 2006-02-05 EST 2006-02-12 EST 2006-02-19 EST [13] 2006-02-26 EST 2006-03-05 EST 2006-03-12 EST 2006-03-19 EST [17] 2006-03-26 EST 2006-04-02 EST seq function (...) UseMethod(seq) environment: namespace:base I am using R 2.2.1 on linux. Why isn't 2006-04-09 in the response of the second call? __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] seq
On Mon, 10 Apr 2006, Omar Lakkis wrote: Can someone, please, help explain to me why the following two calls return the same set: seq(from=as.POSIXlt('2005-12-4'), to=as.POSIXlt('2006-4-2'), by='weeks') [1] 2005-12-04 EST 2005-12-11 EST 2005-12-18 EST 2005-12-25 EST [5] 2006-01-01 EST 2006-01-08 EST 2006-01-15 EST 2006-01-22 EST [9] 2006-01-29 EST 2006-02-05 EST 2006-02-12 EST 2006-02-19 EST [13] 2006-02-26 EST 2006-03-05 EST 2006-03-12 EST 2006-03-19 EST [17] 2006-03-26 EST 2006-04-02 EST seq(from=as.POSIXlt('2005-12-4'), to=as.POSIXlt('2006-4-9'), by='weeks') [1] 2005-12-04 EST 2005-12-11 EST 2005-12-18 EST 2005-12-25 EST [5] 2006-01-01 EST 2006-01-08 EST 2006-01-15 EST 2006-01-22 EST [9] 2006-01-29 EST 2006-02-05 EST 2006-02-12 EST 2006-02-19 EST [13] 2006-02-26 EST 2006-03-05 EST 2006-03-12 EST 2006-03-19 EST [17] 2006-03-26 EST 2006-04-02 EST seq function (...) UseMethod(seq) environment: namespace:base I am using R 2.2.1 on linux. Why isn't 2006-04-09 in the response of the second call? It is because 2006-4-9 happened less than a week after 2006-4-2, because 2006-4-2 was only 23 hours long in your time zone. Use Date if you just want dates, not times. -thomas __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Random specification in LMER
Hello, Can anybody help me understand the difference between the three different codes in specifying the slope in the random part of a mixed model using LMER? Here are the codes: (age | id) (1 + age | id) (age - 1 | id) Thank you in advance Arnaud __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] TukeyHSDs function (pgirmess package)
Rune Vejen Petersen wrote: Dear R-help, I have been trying to use the TukeyHSDs function in the pgirmess package to quickly extract all significant pairwise comparisons in an aov object. However, it seems that this function isn't working as intended when only the two last populations means being tested are significant. An example of this can be seen below: numbers-c(464,482,453,434,495,487) group-gl(3,2,label=c(A,B,C)) testobject-aov(numbers~group) result-TukeyHSD(testobject,conf.level=0.95) error-TukeyHSDs(result) error$group[,1] Error in error$group[, 1] : incorrect number of dimensions To illustrate the normal function, the data set below can be used. numbers-c(845,829,682, 689,581,495) Is there something wrong with this function? Or is there a better way to extract significant comparisons from a tukey test? It looks like the line res[[1]] - x[y, ] in TukeyHSDs() should be replaced with res[[1]] - x[y, , drop = FALSE] Peter Ehlers Cheers, Rune --- Rune Vejen Petersen, M.Sc.Eng. Statens Serum Institute Dept. of Infectious Disease Immunology Artillerivej 5, 81/344 DK-2300 Copenhagen [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] writing a data frame using xtable without row names
Dear all, I am trying to write a data frame / table to a latex table using xtable. The thing is that I do not want to write the row names as not all rows will be named. I have tried writing both a matrix (setting e.g. rownames(mat) - c(a, , )) and a dataframe (setting row.names to a similar setting) to disk, but I still get rows named 1,2,3. Have anyone solved a similar problem? cheers, Monty __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] p values for a GEE model
Hi all, I have a dataset in which the output Y is observed on two groups of patients (treatment factor T with 2 levels). Every subject in each group is observed three times (not time points but just technical replication). I am interested in estimating the treatment effect and take into account the fact that I have repeated measurements for every subject. If I do this with repeated measures ANOVA (in which the patient is considered a random effect) I got the following results: library(nlme) data-read.table(http://146.9.88.18/uploads/dataGEE.txt,header=TRUE) res-lme(Y~T,random=~1|P,data=data) summary(res) So the p-value for significance of the treatment effect is 0.069. I would like to use also as a variant analysis a Generalized Estimation Equation Model, like library(gee) summary(gee(Y~T,id=P,data=data)) Questions: A) Is the gee approach suitable in this case with the model formulae I use? B) Can I obtain a p-value for the fixed effect T ? Thanks, Laurentiu Tarca [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] timeAlign
I use POSIXct for datetimes. Is thee a timeAlign function that I can use where : align by year direction -1 == start of this year direction 1 == start of next year align by week direction -1 == date on last sunday direction 1 == date on next sunday align by day direction -1 == time at past midnight direction 1 == time at this comming midnight __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] passing known medoids to clara() in the cluster package
Thanks for the reply. On Sunday 09 April 2006 11:46 pm, Martin Maechler wrote: DylanB == Dylan Beaudette [EMAIL PROTECTED] on Sun, 9 Apr 2006 19:28:44 -0700 writes: DylanB Greetings, I have had good success using the clara() DylanB function to perform a simple cluster analysis on a DylanB large dataset (1 million+ records with 9 variables). DylanB Since the clara function is a wrapper to pam(), DylanB which will accept known medoid data - I am wondering DylanB if this too is possible with clara() ... The DylanB documentation does not suggest that this is DylanB possible. indeed, it doesn't -- because it's not yet possible. I (as maintainer of cluster) had added the ``known medoid'' option to pam() a while ago last June (for cluster version 1.10.0), and had left a note my TODO file to do the same for clara(). Ah. that would explain things ! :) . I will check back periodically to see when this feature is completed. Unfortunately it's not true that clara() was a wrapper to pam() as you state above. I must have misread the manual pages... Given your wish and clear use case situation, I'm more motivated to approach this particular 'TODO' item! Martin Maechler, ETH Zurich DylanB Essentially I am trying to implement a supervised DylanB classification of numerous geographic data DylanB layers. The unsupervised approach using clara() DylanB works well, but I feel the output classes would be DylanB more meaningful if I were able to let clara() know DylanB about the classes that I have in mind. DylanB Is this at all feasible, or am I trying to DylanB accomplish something that is not possible? Thanks Martin! I will give pam() a try, and see if it can handle the large dataset that I am currently using clara() for -- usually only about 5 seconds are required for clara() to complete. -- Dylan Beaudette Soils and Biogeochemistry Graduate Group University of California at Davis 530.754.7341 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Changing character limit in deparse, as.character and toString
Dear R-help Listers, I am curious if there is some (hopefully easy) way to change the number of characters that can be converted to a single string via any of deparse, as.character or toString. It seems that the limit is 500 for all of these. I saw a previous post where Prof. Ripley suggested that it was a trivial change in the R internals to change as.character's limit from 60 to 500, but I was hoping for something that didn't involve me trying to alter the R internals. Thanks for your help, Dave. -- Dave Armstrong University of Maryland Dept of Government and Politics 3140 Tydings Hall College Park, MD 20742 Office: 2103L Cole Field House Phone: 301-405-9735 e-mail: [EMAIL PROTECTED] web: www.davearmstrong-ps.com [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Configure error
Hi Folks, I sent this message before but I don't think it got through because I wasn't registered. I've been trying for several weeks to install R-2.2.1 on a PC with an AMD Athlon 64 2800*+* processor running Mandriva 2006_64. After unpacking R-2.2.1.tar.gz I ran ./configure However, configure stopped prematurely with the message *configure:27295: WARNING: gfortran and gcc disagree on int and double configure:27297: error: Maybe change CFLAGS or FFLAGS?* Altough I've looked in both the R_Help archive and R Installation and Administration, I can't find any documentation which says what settings should be for CFLAGS or FFLAGS. I tried to mimic the settings shown on page 31 of R Installation and Administration but that failed too.* Does anyone know what the settings should be for this case? Any advice would be greatly appreciated. Richard Carter __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Reshaping genetic data from long to wide
1) I know how to post to the list. You simply send an e-mail to [EMAIL PROTECTED] But how do you read the items and respond to them? I usually read the items at http://tolstoy.newcastle.edu.au/R/help/06/04/index.html#end and then have to jump through some hoops to answer back. Is there any way to access this group through Google Groups or through Outlook express' user group feature? 2)Storing all the SNP data as a string seems quite clever and a space-saving way of doing it. However, if you were to analyze a whole chromosome at a time you would still be creating one almighty big table albeit only temporarily. Do you use R to run TDT analyses? If so, how are you setting up your data frames and then what commands do you issue to analyze what is in your dataframes? I used David Clayton's Stata add on a few months ago and was able to get it to run through the analysis. I ran just one locus. Technically, the analysis seemed to run OK but I want to run all the loci one after the other. Currently I have my data such that I can access it from R through an ODBC connection to Microsoft Access which in turn has an ODBC connection to the Sybase database. Whether I go through strings or not, I still need to find a way that I can assemble it so that a program can systematically run a TDT analysis on all the loci. I can see how strings help me in my storing of the data but that is already a fait acomplis. Can you explain to me how it would help me with sequential analysis of each locus? Do you have any history files so that I can see what you were doing? Farrel Buchinsky, MD Pediatric Otolaryngologist Allegheny General Hospital Pittsburgh, PA ** This email and any files transmitted with it are confidentia...{{dropped}} __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] timeAlign
Try this. dd - Sys.time() # test data lt - as.POSIXlt(dd) ISOdate(1900+lt$year, 1, 1, 0, tz = ) ISOdate(1901+lt$year, 1, 1, 0, tz = ) seq(now, length = 2, by = paste(-, lt$wday, day, sep =))[2] seq(now, length = 2, by = paste(7-lt$wday, day))[2] with(lt, ISOdate(1901+year, mon, mday, 0, tz = )) with(lt, ISOdate(1901+year, mon, mday, 23, 59, 59, tz = ))+1 On 4/10/06, Omar Lakkis [EMAIL PROTECTED] wrote: I use POSIXct for datetimes. Is thee a timeAlign function that I can use where : align by year direction -1 == start of this year direction 1 == start of next year align by week direction -1 == date on last sunday direction 1 == date on next sunday align by day direction -1 == time at past midnight direction 1 == time at this comming midnight __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Reshaping genetic data from long to wide
On 4/10/06, Farrel Buchinsky [EMAIL PROTECTED] wrote: 1) I know how to post to the list. You simply send an e-mail to [EMAIL PROTECTED] But how do you read the items and respond to them? I usually read the items at http://tolstoy.newcastle.edu.au/R/help/06/04/index.html#end and then have to jump through some hoops to answer back. Is there any way to access this group through Google Groups or through Outlook express' user group feature? Try this: http://news.gmane.org/gmane.comp.lang.r.general or one of these: http://dir.gmane.org/gmane.comp.lang.r.general __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] timeAlign
On 4/10/06, Gabor Grothendieck [EMAIL PROTECTED] wrote: Try this. dd - Sys.time() # test data lt - as.POSIXlt(dd) ISOdate(1900+lt$year, 1, 1, 0, tz = ) ISOdate(1901+lt$year, 1, 1, 0, tz = ) seq(now, length = 2, by = paste(-, lt$wday, day, sep =))[2] seq(now, length = 2, by = paste(7-lt$wday, day))[2] The last two lines should be (same as above but the variable name is called lt): seq(lt, length = 2, by = paste(-, lt$wday, day, sep =))[2] seq(lt, length = 2, by = paste(7-lt$wday, day))[2] with(lt, ISOdate(1901+year, mon, mday, 0, tz = )) with(lt, ISOdate(1901+year, mon, mday, 23, 59, 59, tz = ))+1 On 4/10/06, Omar Lakkis [EMAIL PROTECTED] wrote: I use POSIXct for datetimes. Is thee a timeAlign function that I can use where : align by year direction -1 == start of this year direction 1 == start of next year align by week direction -1 == date on last sunday direction 1 == date on next sunday align by day direction -1 == time at past midnight direction 1 == time at this comming midnight __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] problems with rounding in output
Perhaps someone will have a solution to my more general problem, but here is the specific one: I used the round() function to round some estimates to 3 decimal places. I then sent put the rounded estimates in a matrix and used latex() to make a LaTeX table from them. However, in my table, there are estimtes which only have 2 decimal places. I assume that the third decimal place in these numbers was equal to zero, so the round() function simply cut off the superfluous zero. However, I want all of my estimates to have the same number of digits. Is there a way to force R to keep all three digits, even if the last one is zero? Now, getting to the more general issue, to which a solution might negate the need for a solution to the first part of this email. I want to create a table in which all of the standard errors are in parentheses. The solution I used was to input the std. errors into the matrix to be used for making the table as follows paste('(',satt.yr.hrs$se,')',sep='') However, after doing so, my LaTeX output had all of the digits that R output without rounding like it normally does. So, I tried using the round() command as described above. Another problem with my solution is that the negative signs in my LaTeX tables come out as hyphens, not the usual negative signs from math mode. Does anyone have a better solution for how to put my std. errors in parentheses? Thanks, BQ __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] problems with rounding in output
Try: sprintf((%.2f), pi) [1] (3.14) On 4/11/06, Brian Quinif [EMAIL PROTECTED] wrote: Perhaps someone will have a solution to my more general problem, but here is the specific one: I used the round() function to round some estimates to 3 decimal places. I then sent put the rounded estimates in a matrix and used latex() to make a LaTeX table from them. However, in my table, there are estimtes which only have 2 decimal places. I assume that the third decimal place in these numbers was equal to zero, so the round() function simply cut off the superfluous zero. However, I want all of my estimates to have the same number of digits. Is there a way to force R to keep all three digits, even if the last one is zero? Now, getting to the more general issue, to which a solution might negate the need for a solution to the first part of this email. I want to create a table in which all of the standard errors are in parentheses. The solution I used was to input the std. errors into the matrix to be used for making the table as follows paste('(',satt.yr.hrs$se,')',sep='') However, after doing so, my LaTeX output had all of the digits that R output without rounding like it normally does. So, I tried using the round() command as described above. Another problem with my solution is that the negative signs in my LaTeX tables come out as hyphens, not the usual negative signs from math mode. Does anyone have a better solution for how to put my std. errors in parentheses? Thanks, BQ __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html